Abstract: A method for implementing a privacy-preserving automatic speech recognition system using federated learning. The method includes receiving, from respective client devices, at a cloud server, local acoustic model weights for a neural network-based acoustic model of a local automatic speech recognition system running on the respective client devices, wherein the local acoustic model weights are generated at the respective client devices without labelled data, updating a global automatic speech recognition system based on (a) the local acoustic model weights received from the respective client devices and (b) global acoustic model weights of the global automatic speech recognition system derived from labelled data to obtain an updated global automatic speech recognition system, and sending the updated global automatic speech recognition system to the respective client devices to operate as a new local automatic speech recognition system.

Abstract: The present technology pertains to a system, method, and non-transitory computer-readable medium for evaluating the impact of network changes. The technology can detect a temporal event, wherein the temporal event is associated with a change in a network configuration, implementation, or utilization; define a first period prior to the temporal event and a second period posterior to the temporal event; and compare network data collected in the first period and network data collected in the second period.

Abstract: In one example embodiment, acoustic characteristics of a user voice are analyzed by a first machine learning model of a processor. Linguistic patterns in the user voice are analyzed by a second machine learning model of the processor. The user is authenticated with respect to an authorized user by the processor based on analysis of the acoustic characteristics and the linguistic patterns of the user voice by the first and second machine learning models.

Abstract: A method, computer system, and computer program product are provided for synthesizing and/or recognizing speech. Training data is provided to a machine learning model, wherein the training data comprises a plurality of labeled examples of acronyms and initialisms. The machine learning model is trained to classify strings into an acronym class or an initialism class. An input string is classified with the machine learning model into the acronym class or the initialism class. Based on the classifying, a pronunciation is generated for the input string.

Abstract: The disclosed technology relates to a process of providing dynamic machine learning on premise model selection. In particular, a set of machine learned models are generated and provided to an on premise computing device. The machine learned models are generated using a cluster of customer data (e.g. telemetric data) stored on a computing network having different ranges of computational complexity. One of the machine learned models from the set of machine learned models will be selected based on the current available computational resources detected at the on premise computing device. Different machine learned models from the set of machine learned models can then be selected based on changes in the available computational resources and/or customer feedback.

Abstract: Presented herein are systems and methods are presented for detecting out-of-vocabulary (OOV) words in an automatic speech recognition (ASR) system, determining an intended word for the OOV, and adding the intended word to a repository of words. A method may involve receiving audio input data including a series of spoken words; determining that one of the spoken words is an out of vocabulary word absent from a repository of words; generating word candidates based on characteristics of the out of vocabulary word; presenting the word candidates on a display; receiving intended word input data that indicates a selection of one of the word candidates as an intended word for the out of vocabulary word; and adding the intended word to the repository of words. Additionally, one or more devices or apparatuses may be configured to perform such method.

Abstract: The present technology pertains to a system, method, and non-transitory computer-readable medium for evaluating the impact of network changes. The technology can detect a temporal event, wherein the temporal event is associated with a change in a network configuration, implementation, or utilization; define a first period prior to the temporal event and a second period posterior to the temporal event; and compare network data collected in the first period and network data collected in the second period.

Abstract: The present technology pertains to a system, method, and non-transitory computer-readable medium for evaluating the impact of network changes. The technology can detect a temporal event, wherein the temporal event is associated with a change in a network configuration, implementation, or utilization. The technology defines, based on a nature of the temporal event, a first period prior to the temporal event or a second period posterior to the temporal event. The technology compares network data collected in the first period and network data collected in the second period.

Abstract: A method for implementing a privacy-preserving automatic speech recognition system using federated learning. The method includes receiving, from respective client devices, at a cloud server, local acoustic model weights for a neural network-based acoustic model of a local automatic speech recognition system running on the respective client devices, wherein the local acoustic model weights are generated at the respective client devices without labelled data, updating a global automatic speech recognition system based on (a) the local acoustic model weights received from the respective client devices and (b) global acoustic model weights of the global automatic speech recognition system derived from labelled data to obtain an updated global automatic speech recognition system, and sending the updated global automatic speech recognition system to the respective client devices to operate as a new local automatic speech recognition system.

Abstract: Technologies for dynamically generating topology and location based network insights are provided. In some examples, a method can include determining statistical changes in time series data including a series of data points associated with one or more conditions or parameters of a network; determining a period of time corresponding to one or more of the statistical changes in the time series data; obtaining telemetry data corresponding to a segment of the network and one or more time intervals, wherein a respective length of each time interval is based on a length of the period of time corresponding to the one or more of the statistical changes in the time series data; and generating, based on the telemetry data, insights about the segment of the network, the insights identifying a trend or statistical deviation in a behavior of the segment of the network during the one or more time intervals.

Abstract: In one embodiment, a network assurance service executing in a local network clusters measurements obtained from the local network regarding a plurality of devices in the local network into measurement clusters. The network assurance service computes aggregated metrics for each of the measurement clusters. The network assurance service sends a machine learning model computation request to a remote service outside of the local network that includes the aggregated metrics for each of the measurement clusters. The remote service uses the aggregated metrics to train a machine learning-based model to analyze the local network. The network assurance service receives the trained machine learning-based model to analyze performance of the local network. The network assurance service uses the receive machine learning-based model to analyze performance of the local network.

Abstract: In one embodiment, a network assurance service that monitors a network detects anomalies in the network by applying one or more machine learning-based anomaly detectors to telemetry data from the network. The network assurance service receives ranking feedback from a plurality of anomaly rankers regarding relevancy of the detected anomalies. The network assurance service calculates a rescaling factor and quantile parameter by applying an objective function to the ranking feedback, in order to optimize the rescaling factor and quantile parameter of the one or more anomaly detectors. The network assurance service adjusts the rescaling factor and quantile parameter of the one or more anomaly detectors using the calculated rescaling factor and quantile parameter.

Abstract: Technologies for dynamically generating topology and location based network insights are provided. In some examples, a method can include determining statistical changes in time series data including a series of data points associated with one or more conditions or parameters of a network; determining a period of time corresponding to one or more of the statistical changes in the time series data; obtaining telemetry data corresponding to a segment of the network and one or more time intervals, wherein a respective length of each time interval is based on a length of the period of time corresponding to the one or more of the statistical changes in the time series data; and generating, based on the telemetry data, insights about the segment of the network, the insights identifying a trend or statistical deviation in a behavior of the segment of the network during the one or more time intervals.

Abstract: The present technology pertains to a system, method, and non-transitory computer-readable medium for evaluating the impact of network changes. The technology can detect a temporal event, wherein the temporal event is associated with a change in a network configuration, implementation, or utilization. The technology defines, based on a nature of the temporal event, a first period prior to the temporal event or a second period posterior to the temporal event. The technology compares network data collected in the first period and network data collected in the second period.

Abstract: The disclosed technology relates to a process of providing dynamic machine learning on premise model selection. In particular, a set of machine learned models are generated and provided to an on premise computing device. The machine learned models are generated using a cluster of customer data (e.g. telemetric data) stored on a computing network having different ranges of computational complexity. One of the machine learned models from the set of machine learned models will be selected based on the current available computational resources detected at the on premise computing device.

Abstract: In one embodiment, a network assurance service that monitors a plurality of networks obtains characteristic data regarding network entities deployed in the plurality of networks. The network assurance service assigns the network entities to entity clusters by applying a clustering mechanism to the characteristic data regarding the network entities. The network assurance service generates, for each of the entity clusters, a training dataset using the characteristic data for the network entities assigned to that cluster. The network assurance service uses, for each of the entity clusters, the training datasets for an entity cluster to train a machine learning-based model that models the behavior of that entity cluster.

Abstract: In one embodiment, a network assurance service executing in a local network clusters measurements obtained from the local network regarding a plurality of devices in the local network into measurement clusters. The network assurance service computes aggregated metrics for each of the measurement clusters. The network assurance service sends a machine learning model computation request to a remote service outside of the local network that includes the aggregated metrics for each of the measurement clusters. The remote service uses the aggregated metrics to train a machine learning-based model to analyze the local network. The network assurance service receives the trained machine learning-based model to analyze performance of the local network. The network assurance service uses the receive machine learning-based model to analyze performance of the local network.

Abstract: In one embodiment, a network assurance service executing in a local network clusters measurements obtained from the local network regarding a plurality of devices in the local network into measurement clusters. The network assurance service computes aggregated metrics for each of the measurement clusters. The network assurance service sends a machine learning model computation request to a remote service outside of the local network that includes the aggregated metrics for each of the measurement clusters. The remote service uses the aggregated metrics to train a machine learning-based model to analyze the local network. The network assurance service receives the trained machine learning-based model to analyze performance of the local network. The network assurance service uses the receive machine learning-based model to analyze performance of the local network.

Abstract: In one embodiment, a network assurance service executing in a local network clusters measurements obtained from the local network regarding a plurality of devices in the local network into measurement clusters. The network assurance service computes aggregated metrics for each of the measurement clusters. The network assurance service sends a machine learning model computation request to a remote service outside of the local network that includes the aggregated metrics for each of the measurement clusters. The remote service uses the aggregated metrics to train a machine learning-based model to analyze the local network. The network assurance service receives the trained machine learning-based model to analyze performance of the local network. The network assurance service uses the receive machine learning-based model to analyze performance of the local network.

Abstract: In one embodiment, a network assurance service uses a first machine-learning based model that is locally deployed to a network to assess a set of input features comprising measurements from the network. The service monitors, locally in the network, performance of the first machine learning-based model. The service determines that the monitored performance of the first machine learning-based model does not meet one or more performance requirements associated with the network. The service selects a second machine learning-based model for deployment to the network, based on the one or more performance requirements associated with the network and on the set of input features of the first machine learning-based model. The service deploys the selected second machine learning-based model to the network as a replacement for the first machine learning-based model.